示例#1
0
 public IDataView Transform(IDataView input)
 {
     _host.CheckValue(input, nameof(input));
     return(ApplyTransformUtils.ApplyAllTransformsToData(_host, _xf, input));
 }
示例#2
0
        public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
        {
            Contracts.CheckValue(env, nameof(env));
            var host = env.Register("Tree Featurizer Transform");

            host.CheckValue(args, nameof(args));
            host.CheckValue(input, nameof(input));
            host.CheckUserArg(!string.IsNullOrWhiteSpace(args.TrainedModelFile) || args.Trainer != null, nameof(args.TrainedModelFile),
                              "Please specify either a trainer or an input model file.");
            host.CheckUserArg(!string.IsNullOrEmpty(args.FeatureColumn), nameof(args.FeatureColumn), "Transform needs an input features column");

            IDataTransform xf;

            using (var ch = host.Start("Create Tree Ensemble Scorer"))
            {
                var scorerArgs = new TreeEnsembleFeaturizerBindableMapper.Arguments()
                {
                    Suffix = args.Suffix
                };
                if (!string.IsNullOrWhiteSpace(args.TrainedModelFile))
                {
                    if (args.Trainer != null)
                    {
                        ch.Warning("Both an input model and a trainer were specified. Using the model file.");
                    }

                    ch.Trace("Loading model");
                    IPredictor predictor;
                    using (Stream strm = new FileStream(args.TrainedModelFile, FileMode.Open, FileAccess.Read))
                        using (var rep = RepositoryReader.Open(strm, ch))
                            ModelLoadContext.LoadModel <IPredictor, SignatureLoadModel>(host, out predictor, rep, ModelFileUtils.DirPredictor);

                    ch.Trace("Creating scorer");
                    var data = TrainAndScoreTransform.CreateDataFromArgs(ch, input, args);

                    // Make sure that the given predictor has the correct number of input features.
                    if (predictor is CalibratedPredictorBase)
                    {
                        predictor = ((CalibratedPredictorBase)predictor).SubPredictor;
                    }
                    // Predictor should be a FastTreePredictionWrapper, which implements IValueMapper, so this should
                    // be non-null.
                    var vm = predictor as IValueMapper;
                    ch.CheckUserArg(vm != null, nameof(args.TrainedModelFile), "Predictor in model file does not have compatible type");
                    if (vm.InputType.VectorSize != data.Schema.Feature.Type.VectorSize)
                    {
                        throw ch.ExceptUserArg(nameof(args.TrainedModelFile),
                                               "Predictor in model file expects {0} features, but data has {1} features",
                                               vm.InputType.VectorSize, data.Schema.Feature.Type.VectorSize);
                    }

                    var bindable = new TreeEnsembleFeaturizerBindableMapper(env, scorerArgs, predictor);
                    var bound    = bindable.Bind(env, data.Schema);
                    xf = new GenericScorer(env, scorerArgs, input, bound, data.Schema);
                }
                else
                {
                    ch.AssertValue(args.Trainer);

                    ch.Trace("Creating TrainAndScoreTransform");

                    var trainScoreArgs = new TrainAndScoreTransform.Arguments();
                    args.CopyTo(trainScoreArgs);
                    trainScoreArgs.Trainer = args.Trainer;

                    trainScoreArgs.Scorer = ComponentFactoryUtils.CreateFromFunction <IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>(
                        (e, data, mapper, trainSchema) => Create(e, scorerArgs, data, mapper, trainSchema));

                    var mapperFactory = ComponentFactoryUtils.CreateFromFunction <IPredictor, ISchemaBindableMapper>(
                        (e, predictor) => new TreeEnsembleFeaturizerBindableMapper(e, scorerArgs, predictor));

                    var labelInput = AppendLabelTransform(host, ch, input, trainScoreArgs.LabelColumn, args.LabelPermutationSeed);
                    var scoreXf    = TrainAndScoreTransform.Create(host, trainScoreArgs, labelInput, mapperFactory);

                    if (input == labelInput)
                    {
                        return(scoreXf);
                    }
                    return((IDataTransform)ApplyTransformUtils.ApplyAllTransformsToData(host, scoreXf, input, labelInput));
                }
            }
            return(xf);
        }
示例#3
0
 public Transformer(IHostEnvironment env, IDataView input, IDataView view)
 {
     _host = env.Register(nameof(Transformer));
     _xf   = ApplyTransformUtils.ApplyAllTransformsToData(_host, view, new EmptyDataView(_host, input.Schema), input);
 }
            private FoldResult RunFold(int fold)
            {
                var host = GetHost();

                host.Assert(0 <= fold && fold <= _numFolds);
                // REVIEW: Make channels buffered in multi-threaded environments.
                using (var ch = host.Start($"Fold {fold}"))
                {
                    ch.Trace("Constructing trainer");
                    ITrainer trainer = _trainer.CreateInstance(host);

                    // Train pipe.
                    var trainFilter = new RangeFilter.Arguments();
                    trainFilter.Column     = _splitColumn;
                    trainFilter.Min        = (Double)fold / _numFolds;
                    trainFilter.Max        = (Double)(fold + 1) / _numFolds;
                    trainFilter.Complement = true;
                    IDataView trainPipe = new RangeFilter(host, trainFilter, _inputDataView);
                    trainPipe = new OpaqueDataView(trainPipe);
                    var trainData = _createExamples(host, ch, trainPipe, trainer);

                    // Test pipe.
                    var testFilter = new RangeFilter.Arguments();
                    testFilter.Column = trainFilter.Column;
                    testFilter.Min    = trainFilter.Min;
                    testFilter.Max    = trainFilter.Max;
                    ch.Assert(!testFilter.Complement);
                    IDataView testPipe = new RangeFilter(host, testFilter, _inputDataView);
                    testPipe = new OpaqueDataView(testPipe);
                    var testData = _applyTransformsToTestData(host, ch, testPipe, trainData, trainPipe);

                    // Validation pipe and examples.
                    RoleMappedData validData = null;
                    if (_getValidationDataView != null)
                    {
                        ch.Assert(_applyTransformsToValidationData != null);
                        if (!trainer.Info.SupportsValidation)
                        {
                            ch.Warning("Trainer does not accept validation dataset.");
                        }
                        else
                        {
                            ch.Trace("Constructing the validation pipeline");
                            IDataView validLoader = _getValidationDataView();
                            var       validPipe   = ApplyTransformUtils.ApplyAllTransformsToData(host, _inputDataView, validLoader);
                            validPipe = new OpaqueDataView(validPipe);
                            validData = _applyTransformsToValidationData(host, ch, validPipe, trainData, trainPipe);
                        }
                    }

                    // Train.
                    var predictor = TrainUtils.Train(host, ch, trainData, trainer, _trainer.Kind, validData,
                                                     _calibrator, _maxCalibrationExamples, _cacheData, _inputPredictor);

                    // Score.
                    ch.Trace("Scoring and evaluating");
                    var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
                    ch.AssertValue(bindable);
                    var mapper     = bindable.Bind(host, testData.Schema);
                    var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
                    IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);

                    // Save per-fold model.
                    string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
                    if (modelFileName != null && _loader != null)
                    {
                        using (var file = host.CreateOutputFile(modelFileName))
                        {
                            var rmd = new RoleMappedData(
                                CompositeDataLoader.ApplyTransform(host, _loader, null, null,
                                                                   (e, newSource) => ApplyTransformUtils.ApplyAllTransformsToData(e, trainData.Data, newSource)),
                                trainData.Schema.GetColumnRoleNames());
                            TrainUtils.SaveModel(host, ch, file, predictor, rmd, _cmd);
                        }
                    }

                    // Evaluate.
                    var evalComp = _evaluator;
                    if (!evalComp.IsGood())
                    {
                        evalComp = EvaluateUtils.GetEvaluatorType(ch, scorePipe.Schema);
                    }
                    var eval = evalComp.CreateInstance(host);
                    // Note that this doesn't require the provided columns to exist (because of the "opt" parameter).
                    // We don't normally expect the scorer to drop columns, but if it does, we should not require
                    // all the columns in the test pipeline to still be present.
                    var dataEval = new RoleMappedData(scorePipe, testData.Schema.GetColumnRoleNames(), opt: true);

                    var            dict        = eval.Evaluate(dataEval);
                    RoleMappedData perInstance = null;
                    if (_savePerInstance)
                    {
                        var perInst = eval.GetPerInstanceMetrics(dataEval);
                        perInstance = new RoleMappedData(perInst, dataEval.Schema.GetColumnRoleNames(), opt: true);
                    }
                    ch.Done();
                    return(new FoldResult(dict, dataEval.Schema.Schema, perInstance, trainData.Schema));
                }
            }
示例#5
0
        private void RunCore(IChannel ch, string cmd)
        {
            Host.AssertValue(ch);
            Host.AssertNonEmpty(cmd);

            ch.Trace("Constructing trainer");
            ITrainer trainer = _trainer.CreateComponent(Host);

            IPredictor inputPredictor = null;

            if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.InputModelFile, out inputPredictor))
            {
                ch.Warning("No input model file specified or model file did not contain a predictor. The model state cannot be initialized.");
            }

            ch.Trace("Constructing data pipeline");
            IDataView view = CreateLoader();

            ISchema schema  = view.Schema;
            var     label   = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn), _labelColumn, DefaultColumnNames.Label);
            var     feature = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn), _featureColumn, DefaultColumnNames.Features);
            var     group   = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn), _groupColumn, DefaultColumnNames.GroupId);
            var     weight  = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn), _weightColumn, DefaultColumnNames.Weight);
            var     name    = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn), _nameColumn, DefaultColumnNames.Name);

            TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref view, feature, Args.NormalizeFeatures);

            ch.Trace("Binding columns");

            var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
            var data       = new RoleMappedData(view, label, feature, group, weight, name, customCols);

            // REVIEW: Unify the code that creates validation examples in Train, TrainTest and CV commands.
            RoleMappedData validData = null;

            if (!string.IsNullOrWhiteSpace(Args.ValidationFile))
            {
                if (!trainer.Info.SupportsValidation)
                {
                    ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
                }
                else
                {
                    ch.Trace("Constructing the validation pipeline");
                    IDataView validPipe = CreateRawLoader(dataFile: Args.ValidationFile);
                    validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, view, validPipe);
                    validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
                }
            }

            // In addition to the training set, some trainers can accept two extra data sets, validation set and test set,
            // in training phase. The major difference between validation set and test set is that training process may
            // indirectly use validation set to improve the model but the learned model should totally independent of test set.
            // Similar to validation set, the trainer can report the scores computed using test set.
            RoleMappedData testDataUsedInTrainer = null;

            if (!string.IsNullOrWhiteSpace(Args.TestFile))
            {
                // In contrast to the if-else block for validation above, we do not throw a warning if test file is provided
                // because this is TrainTest command.
                if (trainer.Info.SupportsTest)
                {
                    ch.Trace("Constructing the test pipeline");
                    IDataView testPipeUsedInTrainer = CreateRawLoader(dataFile: Args.TestFile);
                    testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, view, testPipeUsedInTrainer);
                    testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
                }
            }

            var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
                                             Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor, testDataUsedInTrainer);

            using (var file = Host.CreateOutputFile(Args.OutputModelFile))
                TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);
        }
        private void RunCore(IChannel ch, string cmd)
        {
            Host.AssertValue(ch);
            Host.AssertNonEmpty(cmd);

            ch.Trace("Constructing trainer");
            ITrainer trainer = Args.Trainer.CreateInstance(Host);

            IPredictor inputPredictor = null;

            if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.InputModelFile, out inputPredictor))
            {
                ch.Warning("No input model file specified or model file did not contain a predictor. The model state cannot be initialized.");
            }

            ch.Trace("Constructing the training pipeline");
            IDataView trainPipe = CreateLoader();

            ISchema schema = trainPipe.Schema;
            string  label  = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
                                                                 Args.LabelColumn, DefaultColumnNames.Label);
            string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
                                                                  Args.FeatureColumn, DefaultColumnNames.Features);
            string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
                                                               Args.GroupColumn, DefaultColumnNames.GroupId);
            string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
                                                                Args.WeightColumn, DefaultColumnNames.Weight);
            string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
                                                              Args.NameColumn, DefaultColumnNames.Name);

            TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, Args.NormalizeFeatures);

            ch.Trace("Binding columns");
            var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
            var data       = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);

            RoleMappedData validData = null;

            if (!string.IsNullOrWhiteSpace(Args.ValidationFile))
            {
                if (!TrainUtils.CanUseValidationData(trainer))
                {
                    ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
                }
                else
                {
                    ch.Trace("Constructing the validation pipeline");
                    IDataView validPipe = CreateRawLoader(dataFile: Args.ValidationFile);
                    validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, validPipe);
                    validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
                }
            }

            var predictor = TrainUtils.Train(Host, ch, data, trainer, _info.LoadNames[0], validData,
                                             Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor);

            IDataLoader testPipe;

            using (var file = !string.IsNullOrEmpty(Args.OutputModelFile) ?
                              Host.CreateOutputFile(Args.OutputModelFile) : Host.CreateTempFile(".zip"))
            {
                TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);

                ch.Trace("Constructing the testing pipeline");
                using (var stream = file.OpenReadStream())
                    using (var rep = RepositoryReader.Open(stream, ch))
                        testPipe = LoadLoader(rep, Args.TestFile, true);
            }

            // Score.
            ch.Trace("Scoring and evaluating");
            IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);

            // Evaluate.
            var evalComp = Args.Evaluator;

            if (!evalComp.IsGood())
            {
                evalComp = EvaluateUtils.GetEvaluatorType(ch, scorePipe.Schema);
            }
            var evaluator = evalComp.CreateInstance(Host);
            var dataEval  = new RoleMappedData(scorePipe, label, features,
                                               group, weight, name, customCols, opt: true);
            var metrics = evaluator.Evaluate(dataEval);

            MetricWriter.PrintWarnings(ch, metrics);
            evaluator.PrintFoldResults(ch, metrics);
            if (!metrics.TryGetValue(MetricKinds.OverallMetrics, out var overall))
            {
                throw ch.Except("No overall metrics found");
            }
            overall = evaluator.GetOverallResults(overall);
            MetricWriter.PrintOverallMetrics(Host, ch, Args.SummaryFilename, overall, 1);
            evaluator.PrintAdditionalMetrics(ch, metrics);
            Dictionary <string, IDataView>[] metricValues = { metrics };
            SendTelemetryMetric(metricValues);
            if (!string.IsNullOrWhiteSpace(Args.OutputDataFile))
            {
                var perInst     = evaluator.GetPerInstanceMetrics(dataEval);
                var perInstData = new RoleMappedData(perInst, label, null, group, weight, name, customCols);
                var idv         = evaluator.GetPerInstanceDataViewToSave(perInstData);
                MetricWriter.SavePerInstance(Host, ch, Args.OutputDataFile, idv);
            }
        }
示例#7
0
 public IDataView Transform(IDataView input) => ApplyTransformUtils.ApplyAllTransformsToData(_env, _xf, input);
        private void RunCore(IChannel ch, string cmd)
        {
            Host.AssertValue(ch);
            Host.AssertNonEmpty(cmd);

            ch.Trace("Constructing trainer");
            ITrainer trainer = Args.Trainer.CreateComponent(Host);

            IPredictor inputPredictor = null;

            if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.InputModelFile, out inputPredictor))
            {
                ch.Warning("No input model file specified or model file did not contain a predictor. The model state cannot be initialized.");
            }

            ch.Trace("Constructing the training pipeline");
            IDataView trainPipe = CreateLoader();

            ISchema schema = trainPipe.Schema;
            string  label  = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
                                                                 Args.LabelColumn, DefaultColumnNames.Label);
            string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
                                                                  Args.FeatureColumn, DefaultColumnNames.Features);
            string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
                                                               Args.GroupColumn, DefaultColumnNames.GroupId);
            string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
                                                                Args.WeightColumn, DefaultColumnNames.Weight);
            string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
                                                              Args.NameColumn, DefaultColumnNames.Name);

            TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, Args.NormalizeFeatures);

            ch.Trace("Binding columns");
            var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
            var data       = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);

            RoleMappedData validData = null;

            if (!string.IsNullOrWhiteSpace(Args.ValidationFile))
            {
                if (!trainer.Info.SupportsValidation)
                {
                    ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
                }
                else
                {
                    ch.Trace("Constructing the validation pipeline");
                    IDataView validPipe = CreateRawLoader(dataFile: Args.ValidationFile);
                    validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, validPipe);
                    validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
                }
            }

            // In addition to the training set, some trainers can accept two data sets, validation set and test set,
            // in training phase. The major difference between validation set and test set is that training process may
            // indirectly use validation set to improve the model but the learned model should totally independent of test set.
            // Similar to validation set, the trainer can report the scores computed using test set.
            RoleMappedData testDataUsedInTrainer = null;

            if (!string.IsNullOrWhiteSpace(Args.TestFile))
            {
                // In contrast to the if-else block for validation above, we do not throw a warning if test file is provided
                // because this is TrainTest command.
                if (trainer.Info.SupportsTest)
                {
                    ch.Trace("Constructing the test pipeline");
                    IDataView testPipeUsedInTrainer = CreateRawLoader(dataFile: Args.TestFile);
                    testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, testPipeUsedInTrainer);
                    testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
                }
            }

            var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
                                             Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor, testDataUsedInTrainer);

            IDataLoader testPipe;
            bool        hasOutfile   = !string.IsNullOrEmpty(Args.OutputModelFile);
            var         tempFilePath = hasOutfile ? null : Path.GetTempFileName();

            using (var file = new SimpleFileHandle(ch, hasOutfile ? Args.OutputModelFile : tempFilePath, true, !hasOutfile))
            {
                TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);
                ch.Trace("Constructing the testing pipeline");
                using (var stream = file.OpenReadStream())
                    using (var rep = RepositoryReader.Open(stream, ch))
                        testPipe = LoadLoader(rep, Args.TestFile, true);
            }

            // Score.
            ch.Trace("Scoring and evaluating");
            ch.Assert(Args.Scorer == null || Args.Scorer is ICommandLineComponentFactory, "TrainTestCommand should only be used from the command line.");
            IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);

            // Evaluate.
            var evaluator = Args.Evaluator?.CreateComponent(Host) ??
                            EvaluateUtils.GetEvaluator(Host, scorePipe.Schema);
            var dataEval = new RoleMappedData(scorePipe, label, features,
                                              group, weight, name, customCols, opt: true);
            var metrics = evaluator.Evaluate(dataEval);

            MetricWriter.PrintWarnings(ch, metrics);
            evaluator.PrintFoldResults(ch, metrics);
            if (!metrics.TryGetValue(MetricKinds.OverallMetrics, out var overall))
            {
                throw ch.Except("No overall metrics found");
            }
            overall = evaluator.GetOverallResults(overall);
            MetricWriter.PrintOverallMetrics(Host, ch, Args.SummaryFilename, overall, 1);
            evaluator.PrintAdditionalMetrics(ch, metrics);
            Dictionary <string, IDataView>[] metricValues = { metrics };
            SendTelemetryMetric(metricValues);
            if (!string.IsNullOrWhiteSpace(Args.OutputDataFile))
            {
                var perInst     = evaluator.GetPerInstanceMetrics(dataEval);
                var perInstData = new RoleMappedData(perInst, label, null, group, weight, name, customCols);
                var idv         = evaluator.GetPerInstanceDataViewToSave(perInstData);
                MetricWriter.SavePerInstance(Host, ch, Args.OutputDataFile, idv);
            }
        }